By Topic

1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition

21-23 June 1994

Filter Results

Displaying Results 1 - 25 of 166
  • Proceedings of IEEE Conference on Computer Vision and Pattern Recognition

    Publication Year: 1994
    Request permission for commercial reuse | PDF file iconPDF (51 KB)
    Freely Available from IEEE
  • Recognizing object function through reasoning about 3-D shape and dynamic physical properties

    Publication Year: 1994, Page(s):546 - 553
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (912 KB)

    Recent work in computer vision has demonstrated positive results in reasoning about possible object function based on analysis of only the object shape. While shape properties are important, verification of actual functionality generally requires consideration of properties beyond pure static shape. In particular, dynamic physical properties such as the degree of deformation or rigidity under appl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Realistic range rendering

    Publication Year: 1994, Page(s):848 - 851
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (332 KB)

    In many model-based object recognition systems, a synthesize-and-verify technique is used to evaluate the quality of hypotheses. This technique synthesises images of hypothesized objects in hypothesized poses, and compares them against the input imagery, producing a matching score. In this paper, we examine the image synthesis process in the context of triangulation-based range finding. We motivat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Depth from focus with one image

    Publication Year: 1994, Page(s):713 - 717
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    A novel depth-from-focus technique is introduced that needs only a single image. It is based on a precise knowledge of the 3-D point spread function and requires objects of uniform brightness and simple shapes. Using adequate low-level image processing techniques, the true area of the object and the distance from the focal plane is obtained from parameters such as the apparent (blurred) area of th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A study relating image sampling rate and image pattern recognition

    Publication Year: 1994, Page(s):709 - 712
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (276 KB)

    The trade-off between the granularity of the data representation and the recognition accuracy is examined in this paper. We show that unless a particular criterion is satisfied, there is no guarantee of achieving a prescribed recognition accuracy. This criterion of interest, is the mutual information content between the measurements and the class identities. A novel method for the objective evalua... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A practical pattern recognition system for translation, scale and rotation invariance

    Publication Year: 1994, Page(s):391 - 396
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB)

    We present a practical pattern recognition system that is invariant with respect to translation, scale and rotation of objects. The system is also insensitive to large variations of the threshold used. As feature vectors, Zernike moments are used and we compare them with Hu's seven moment invariants. For a practical machine vision system, three key issues are discussed: pattern normalization, fast... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new closed-form solution for absolute orientation

    Publication Year: 1994, Page(s):129 - 134
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    Presents a closed-form solution for the determination of 3D displacement and rotation parameters, given a set of 3D point correspondences. The method applies to the general case of arbitrary displacement and rotation with respect to an arbitrary stationary scene. The approach is based on the linear subspace method, which allows separate linear equations to be extracted for the displacement and rot... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Blended deformable models

    Publication Year: 1994, Page(s):566 - 572
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (564 KB)

    We develop a new class of parameterized models based on the linear interpolation of two parameterized shapes using a blending function. Using a small number of additional parameters, blending extends the coverage of shape primitives. In particular, it offers the ability to construct shapes whose genus can change. Blended models are incorporated into a physics-based shape estimation framework which... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Document image understanding: geometric and logical layout

    Publication Year: 1994, Page(s):385 - 390
    Cited by:  Papers (39)  |  Patents (21)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (632 KB)

    Document image understanding encompasses the technology required to make paper documents equivalent to other computer exchange media like floppies, tapes, and CDROMs. The physical reader of the paper document is the scanner just like the physical reader of the floppy is the floppy drive and the physical reader of the tape cartridge is the tape cartridge drive, and the physical reader of the CDROM ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Medium level scene representation using a VLSI smart hexagonal sensor with multiresolution edge extraction capability and scale space integration processing

    Publication Year: 1994, Page(s):632 - 637
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (588 KB)

    This paper presents a sensing approach where photo-transduction, multi-resolution feature extraction, scale-space integration and edge tracking are performed on a mixed (digital-analog) VLSI architecture in order to generate medium-level scene description. The proposed system is mainly targeted for robot vision applications where feature description is preferred to a set of raw or raster 2D images... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Registration without correspondences

    Publication Year: 1994, Page(s):121 - 128
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (700 KB)

    We present a method for registering images of complex 3D surfaces that does not require explicit correspondences between features across the images. Our method relies on the use of a full 3D model of the surface to adjust the position and orientation of the camera by minimizing an objective function based on the projections of the images onto the model. This approach constrains the camera paramete... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MDL-based spatiotemporal segmentation from motion in a long image sequence

    Publication Year: 1994, Page(s):448 - 453
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (516 KB)

    This paper presents a method for spatiotemporal segmentation of long sequences of images which include multiple independently moving objects, based on the Minimum Description Length (MDL) principle. Spatiotemporal (ST) segments in the image sequence are extracted, each of which consists of edge segments having similar motions. First, we construct a family of motion models, each of which is complet... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Principal component analysis with missing data and its application to object modeling

    Publication Year: 1994, Page(s):560 - 565
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    Observation-based modeling can reduce the cost and effort of model constructions for tasks such as virtual reality environment. Object modeling from a sequence of range images has been formulated as a problem of principal component analysis with missing data (PCAMD), which can be generalized as a weighted least square (WLS) minimization problem. After all visible regions appeared over the whole se... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Overcomplete steerable pyramid filters and rotation invariance

    Publication Year: 1994, Page(s):222 - 228
    Cited by:  Papers (84)  |  Patents (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (588 KB)

    A given (overcomplete) discrete oriented pyramid may be converted into a steerable pyramid by interpolation. We present a technique for deriving the optimal interpolation functions (otherwise called `steering coefficients'). The proposed scheme is demonstrated on a computationally efficient oriented pyramid, which is a variation on the Burt and Adelson (1983) pyramid. We apply the generated steera... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning indexing functions for 3-D model-based object recognition

    Publication Year: 1994, Page(s):275 - 280
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (496 KB)

    Indexing is an efficient method of recovering match hypotheses in model-based object recognition. Unlike other methods, which search for viewpoint-invariant shape descriptors to use as indices, we use a learning method to model the smooth variation in appearance of local feature sets (LFS). Indexing from LFS effectively deals with the problems of occlusion and missing features. The indexing functi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of shape from shading techniques

    Publication Year: 1994, Page(s):377 - 384
    Cited by:  Papers (28)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (672 KB)

    Since the first shape-from-shading technique was developed by B.K.P. Horn in the early 1970s, different approaches have been continuously emerging in the past two decades. Some of them, improve existing techniques, while others are completely new approaches. However, there is no literature on, the comparison and performance analysis of these techniques. This paper provides comparison and analysis ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Voronoi diagrams of polygons: A framework for shape representation

    Publication Year: 1994, Page(s):638 - 643
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (540 KB)

    This paper describes an efficient shape representation framework for planar shapes using Voronoi skeletons. A new algorithm for the construction of the Voronoi diagram of a polygon with holes is first described. The main features of this algorithm are its robustness in handling the standard degenerate cases (colinearity of more than two points; co-circularity of more than three points), and its ea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The extruded generalized cylinder: a deformable model for object recovery

    Publication Year: 1994, Page(s):174 - 181
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (608 KB)

    There is increasing interest in the recovery of generalized cylinders (GCs) with curved spines. However, existing formulations of such GCs, for example those based an the Frenet-Serret frame or the tube model, suffer serious drawbacks: discontinuities, a lack of expressive power, ”narrowing” in the plane normal to the spine, non-intuitive twisting behavior, and/or off-axis nonorthogona... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new method to calculate looming for autonomous obstacle avoidance

    Publication Year: 1994, Page(s):777 - 780
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (344 KB)

    The concept of visual looming can be used as a powerful visual cue for autonomous obstacle avoidance. In this paper a method that measures looming quantitatively by fixating a camera at a point on the surface of an object is presented. It is based on studying the texture and its temporal change near the fixation point. The surface may be tilted relative to the optical axis. Looming can be calculat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Geometric heat equation and nonlinear diffusion of shapes and images

    Publication Year: 1994, Page(s):113 - 120
    Cited by:  Papers (15)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (780 KB)

    We propose a geometric smoothing method based on local curvature in shapes and images which is governed by the geometric heat equation and is a special case of the reaction-diffusion framework proposed by Faugeras (1990). For shapes, the approach is analogous to the classical heat equation smoothing, but with a renormalization by arc-length at each infinitesimal step. For images, the smoothing is ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The development of the Image Understanding Environment

    Publication Year: 1994, Page(s):443 - 447
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (476 KB)

    The Image Understanding Environment (IUE) project is a five year program, sponsored by ARPA, to develop a common object-oriented software environment for the development of algorithms and application systems. This paper reviews the design of this system and provides an overview of the distributed implementation effort currently underway at Amerinex AI, Advanced Decision Systems, Carnegie Mellon Un... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Qualitative obstacle detection

    Publication Year: 1994, Page(s):554 - 559
    Cited by:  Papers (10)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (448 KB)

    Three different algorithms for qualitative obstacle detection are presented in this paper. Each one is based on different assumptions. The first two algorithms are aimed at yes/no obstacle detection without indicating which points are obstacles. They have the advantage of fast determination of the existence of obstacles in a scene based on the solvability of a linear system. The first algorithm us... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A survey of motion analysis from moving light displays

    Publication Year: 1994, Page(s):214 - 221
    Cited by:  Papers (18)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (740 KB)

    Motion-based recognition deals with the recognition of objects or motions directly from the motion information extracted from a sequence of images. There are two main steps in this approach. The first consists of finding an appropriate representation for the objects or motions, from the motion cues of the sequence, and then organize them into useful representations. The second step consists of the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Closed-form attitude determination under spectrally varying illumination

    Publication Year: 1994, Page(s):985 - 990
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (620 KB)

    When a Lambertian surface is illuminated by several chromatic lights the surface normals may be recovered from a single color image. A robust regression is used to find the ellipsoid in color space on which at least half the pixels lie. Then the matrix giving the linear relationship between the color and the surface normal, for non-outlier points is found as a root of the ellipsoid quadratic form.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robot pose estimation in unknown environments by matching 2D range scans

    Publication Year: 1994, Page(s):935 - 938
    Cited by:  Papers (49)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (304 KB)

    We develop two algorithms to register a range scan to a previous scan so as to compute relative robot positions in an unknown environment. The first algorithm is used on matching tangent lines defined on two scans and minimizing a distance function. The second algorithm iteratively establishes correspondences between points in the two scans and then solves the point-to-point least-squares problem ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.